Reliability, availability, and serviceability
The reliability, availability, and serviceability (RAS) infrastructure provides the means to report events that occur on the hardware and in the software on the Blue Gene/Q system. A predefined set of messages are built in, but the design also allows users to define their own RAS events and log them to the database. RAS events can be viewed and queried through Blue Gene Navigator (See section 2.2.8, “RAS” on page 17
7.1 Elements of a RAS message
Blue Gene/Q RAS messages contain basic information, ...